NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED451209
Record Type: Non-Journal
Publication Date: 2001-Feb
Pages: 23
Abstractor: N/A
Reference Count: N/A
ISBN: N/A
ISSN: N/A
Understanding Variance Contributions to Overall Canonical Correlation Effects: Canonical Commonality Analysis.
Si, Ching-Fung Benjamin
Applying commonality analysis to canonical correlation analysis is part of a trend toward the use of multivariate statistical methods enhanced by the ease of computation provided by computer software. Several recent papers have discussed canonical commonality analysis. This paper summarizes developments in the field and uses a data set to demonstrate how canonical commonality analysis sheds light on the interpretation of the model effect. The paper also provides guidelines for the deletion of predictors in canonical correlation analysis. Canonical commonality analysis honors the multivariate context and preserves the level of scale of the variables. It would be useful when the number of predictors is less than 5. An appendix contains the Statistical Package for the Social Sciences syntax for the canonical commonality analysis. (Contains 3 tables and 11 references.) (Author/SLD)
Publication Type: Reports - Descriptive; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A